train_utils.py 6.76 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
# @author lucasmiranda42
# encoding: utf-8
# module deepof

"""

Simple utility functions used in deepof example scripts. These are not part of the main package

"""
from datetime import datetime

from kerastuner import BayesianOptimization
13
from kerastuner_tensorboard_logger import TensorBoardLogger
14
from typing import Tuple, Union, Any, List
15
16
17
18
19
20
21
22
import deepof.hypermodels
import deepof.model_utils
import numpy as np
import os
import pickle
import tensorflow as tf


23
def load_hparams(hparams):
24
25
26
27
28
29
30
31
32
33
34
35
    """Loads hyperparameters from a custom dictionary pickled on disc.
    Thought to be used with the output of hyperparameter_tuning.py"""

    if hparams is not None:
        with open(hparams, "rb") as handle:
            hparams = pickle.load(handle)
    else:
        hparams = {
            "units_conv": 256,
            "units_lstm": 256,
            "units_dense2": 64,
            "dropout_rate": 0.25,
36
            "encoding": 16,
37
38
39
40
41
42
43
44
45
46
47
48
            "learning_rate": 1e-3,
        }
    return hparams


def load_treatments(train_path):
    """Loads a dictionary containing the treatments per individual,
    to be loaded as metadata in the coordinates class"""
    try:
        with open(
            os.path.join(
                train_path,
49
                [i for i in os.listdir(train_path) if i.endswith(".pkl")][0],
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
            ),
            "rb",
        ) as handle:
            treatment_dict = pickle.load(handle)
    except IndexError:
        treatment_dict = None

    return treatment_dict


def get_callbacks(
    X_train: np.array,
    batch_size: int,
    variational: bool,
    predictor: float,
    k: int,
    loss: str,
    kl_wu: int,
    mmd_wu: int,
) -> Tuple:
    """Generates callbacks for model training, including:
        - run_ID: run name, with coarse parameter details;
        - tensorboard_callback: for real-time visualization;
        - cp_callback: for checkpoint saving,
        - onecycle: for learning rate scheduling"""

    run_ID = "{}{}{}{}{}{}_{}".format(
        ("GMVAE" if variational else "AE"),
        ("P" if predictor > 0 and variational else ""),
        ("_components={}".format(k) if variational else ""),
        ("_loss={}".format(loss) if variational else ""),
        ("_kl_warmup={}".format(kl_wu) if variational else ""),
        ("_mmd_warmup={}".format(mmd_wu) if variational else ""),
        datetime.now().strftime("%Y%m%d-%H%M%S"),
    )

    log_dir = os.path.abspath("logs/fit/{}".format(run_ID))
87
    tensorboard_callback = tf.keras.callbacks.TensorBoard(
88
89
90
        log_dir=log_dir, histogram_freq=1, profile_batch=2,
    )

91
92
93
94
95
96
    cp_callback = tf.keras.callbacks.ModelCheckpoint(
        "./logs/checkpoints/" + run_ID + "/cp-{epoch:04d}.ckpt",
        verbose=1,
        save_best_only=False,
        save_weights_only=True,
        save_freq="epoch",
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
    )

    onecycle = deepof.model_utils.one_cycle_scheduler(
        X_train.shape[0] // batch_size * 250, max_rate=0.005,
    )

    return run_ID, tensorboard_callback, cp_callback, onecycle


def tune_search(
    train: np.array,
    test: np.array,
    bayopt_trials: int,
    hypermodel: str,
    k: int,
    kl_wu: int,
    loss: str,
    mmd_wu: int,
    overlap_loss: float,
    predictor: float,
    project_name: str,
118
    callbacks: List,
119
    n_epochs: int = 40,
120
    n_replicas: int = 1,
121
) -> Union[bool, Tuple[Any, Any]]:
122
123
124
125
126
127
    """Define the search space using keras-tuner and bayesian optimization

        Parameters:
            - train (np.array): dataset to train the model on
            - test (np.array): dataset to validate the model on
            - bayopt_trials (int): number of Bayesian optimization iterations to run
128
129
            - hypermodel (str): hypermodel to load. Must be one of S2SAE (plain autoencoder)
            or S2SGMVAE (Gaussian Mixture Variational autoencoder).
130
131
132
133
134
135
136
137
138
139
            - k (int) number of components of the Gaussian Mixture
            - kl_wu (int): number of epochs for KL divergence warm up
            - loss (str): one of [ELBO, MMD, ELBO+MMD]
            - mmd_wu (int): number of epochs for MMD warm up
            - overlap_loss (float): assigns as weight to an extra loss term which
            penalizes overlap between GM components
            - predictor (float): adds an extra regularizing neural network to the model,
            which tries to predict the next frame from the current one
            - project_name (str): ID of the current run
            - callbacks (list): list of callbacks for the training loop
140
141
142
            - n_epochs (int): optional. Number of epochs to train each run for
            - n_replicas (int): optional. Number of replicas per parameter set. Higher values
             will yield more robust results, but will affect performance severely
143
144
145
146
147
148
149

        Returns:
            - best_hparams (dict): dictionary with the best retrieved hyperparameters
            - best_run (tf.keras.Model): trained instance of the best model found

    """

lucas_miranda's avatar
lucas_miranda committed
150
    if hypermodel == "S2SAE":  # pragma: no cover
151
152
153
154
155
156
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_AE(input_shape=train.shape)

    elif hypermodel == "S2SGMVAE":
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_GMVAE(
            input_shape=train.shape,
            kl_warmup_epochs=kl_wu,
157
            loss=loss,
158
            mmd_warmup_epochs=mmd_wu,
159
            number_of_components=k,
160
            overlap_loss=overlap_loss,
161
            predictor=predictor,
162
        )
lucas_miranda's avatar
lucas_miranda committed
163

164
165
166
167
        # if "ELBO" in loss and kl_wu > 0:
        #     callbacks.append(hypermodel.kl_warmup_callback)
        # if "MMD" in loss and mmd_wu > 0:
        #     callbacks.append(hypermodel.mmd_warmup_callback)
lucas_miranda's avatar
lucas_miranda committed
168

169
170
171
172
173
    else:
        return False

    tuner = BayesianOptimization(
        hypermodel,
174
        directory="BayesianOptx",
175
        executions_per_trial=n_replicas,
176
177
        logger=TensorBoardLogger(metrics=["val_mae"], logdir="./logs/hparams"),
        max_trials=bayopt_trials,
178
179
        objective="val_mae",
        project_name=project_name,
180
        seed=42,
181
182
183
184
185
    )

    print(tuner.search_space_summary())

    tuner.search(
lucas_miranda's avatar
lucas_miranda committed
186
        train if predictor == 0 else [train[:-1]],
lucas_miranda's avatar
lucas_miranda committed
187
        train if predictor == 0 else [train[:-1], train[1:]],
188
        epochs=n_epochs,
lucas_miranda's avatar
lucas_miranda committed
189
190
191
        validation_data=(
            (test, test) if predictor == 0 else (test[:-1], [test[:-1], test[1:]])
        ),
192
193
        verbose=1,
        batch_size=256,
lucas_miranda's avatar
lucas_miranda committed
194
        callbacks=callbacks,
195
196
197
198
199
    )

    best_hparams = tuner.get_best_hyperparameters(num_trials=1)[0]
    best_run = tuner.hypermodel.build(best_hparams)

lucas_miranda's avatar
lucas_miranda committed
200
201
    print(tuner.results_summary())

202
203
204
205
206
207
208
209
    return best_hparams, best_run


# TODO:
#    - load_treatments should be part of the main data module. If available in the main directory,
#    a table (preferrable in csv) should be loaded as metadata of the coordinates automatically.
#    This becomes particularly important por the supervised models that include phenotype classification
#    alongside the encoding.